The result you are building

Finished Result:

A per-task budget policy and scorecard that predicts maximum spend and deadline, records actual contribution by step, degrades safely, and stops workflows whose expected value, quality, or remaining budget is insufficient.

Use this guide when

Agents call multiple models, APIs, paid x402 resources, browsers, or people.
Latency or cost varies significantly by route and retry.
You need defensible routing and price decisions instead of selecting the cheapest headline model.

Do not use it as a substitute for

Optimizing token price while ignoring tool, failure, review, and opportunity cost.
Allowing retries or parallel fan-out to spend an unbounded budget.

Before you change anything

Collect these items first. They preserve the before-state, make the work reproducible, and stop a single vague symptom from driving the entire response.

Task classes, required quality, deadline, and economic value.
Model/tool/data prices, quotas, p50/p95 latency, and failure rates.
Prompt/input/output sizes and cache behavior.
Retry, parallelism, human review, and paid-failure policy.
Historical quality, abstention, correction, and end-to-end success by route.

Stop Before Proceeding:

Stop a task before the next paid action when worst-case remaining cost exceeds the authorized cap, the deadline cannot be met, or the available route cannot meet the minimum quality and safety checks.

Understand the system before fixing it

Capability is not authority A tool may be technically able to act while policy, budget, ownership, or user intent still forbids the action. Keep execution permission explicit and revocable.

Deterministic boundaries contain probabilistic reasoning Models may propose plans, but schemas, allowlists, budgets, approvals, idempotency, and postconditions must decide what can actually happen.

Unit economics are end to end Include model tokens, tools, data, network, payment fees, failed attempts, review, storage, support, and refunded or unusable outputs.

Cheapest valid route beats cheapest call A low-cost call that triggers retries, correction, or bad action can be more expensive than a stronger route that succeeds once.

Evidence-to-decision map

Start with the row that most closely matches the evidence. The first test isolates a layer; it is not permission to
make every available change.

   Evidence                Likely layer      First decisive check              What the result means

   Token spend is low      Tool/review       Allocate every cost to task and   Non-model calls, retries, or human correction dominate.
   but task cost is high   cost              step

   p50 fast but users      Tail latency      Trace p95/p99 critical path       A slow dependency or sequential chain controls completion.
   time out

   Cache saves money       Freshness         Compare cache age to task         Cost optimization violates the answer contract.
   but answers stale       policy            requirement

   Parallel agents         Fan-out           Calculate worst-case branch       Budget enforcement happens after calls rather than before
   exceed cap                                spend                             reservation.

   Cheap model             Quality routing   Compare end-to-end success        Per-call price is the wrong objective.
   produces more fixes                       and correction cost

Step-by-step procedure

Work in order and retain the output from each step. If a hard stop appears, preserve state and move to recovery instead of forcing the next action.

01 Define task value and minimum quality Why: A precise boundary prevents a plausible fix from solving the wrong problem.

Do: Classify tasks by consequence, required accuracy, freshness, deadline, privacy, and maximum economically rational spend.

Read the result: Each task class has a quality floor and hard spend/deadline cap.